YOLOv8数据集划分代码
1.splitDataset.py文件
import os
import random
trainval_percent = 0.9
train_percent = 0.9
xmlfilepath = './data/Annotations'
txtsavepath = 'data/ImageSets'
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open('data/ImageSets/trainval.txt', 'w')
ftest = open('data/ImageSets/test.txt', 'w')
ftrain = open('data/ImageSets/train.txt', 'w')
fval = open('data/ImageSets/val.txt', 'w')
for i in list:
name = total_xml[i][:-4] + '\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
2.XML2TXT.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test', 'val']
classes = ['1','2','3','4']
def convert(size, box):
dw = 1./size[0]
dh = 1./size[1]
x = (box[0] + box[1])/2.0
y = (box[2] + box[3])/2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
return (x, y, w, h)
def convert_annotation(image_id):
'''
将对应文件名的xml文件转化为label文件,xml文件包含了对应的bunding框以及图片长款大小等信息,
通过对其解析,然后进行归一化最终读到label文件中去,也就是说
一张图片文件对应一个xml文件,然后通过解析和归一化,能够将对应的信息保存到唯一一个label文件中去
labal文件中的格式:calss x y w h 同时,一张图片对应的类别有多个,所以对应的bunding的信息也有多个
'''
in_file = open('data/Annotations/%s.xml' % (image_id), encoding='utf-8')
out_file = open('data/labels/%s.txt' % (image_id), 'w', encoding='utf-8')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
if size != None:
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
print(image_id, cls, b)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
print(wd)
for image_set in sets:
'''
对所有的文件数据集进行遍历
做了两个工作:
1.将所有图片文件都遍历一遍,并且将其所有的全路径都写在对应的txt文件中去,方便定位
2.同时对所有的图片文件进行解析和转化,将其对应的bundingbox 以及类别的信息全部解析写到label 文件中去
最后再通过直接读取文件,就能找到对应的label 信息
'''
if not os.path.exists('data/labels/'):
os.makedirs('data/labels/')
image_ids = open('data/ImageSets/%s.txt' % (image_set)).read().strip().split()
list_file = open('data/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write('data/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()